NUIG at TIAD 2021: Cross-lingual Word Embeddings for Translation Inference

Sina Ahmadi; Atul Kumar Ojha; Shubhanker Banerjee; John Philip McCrae

doi:10.13025/nxqc-n767

NUIG at TIAD 2021: Cross-lingual Word Embeddings for Translation Inference

Sina Ahmadi
, Atul Kumar Ojha
, Shubhanker Banerjee
, John Philip McCrae

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

Inducing new translation pairs across dictionaries is an important task that facilitates processing and maintaining lexicographical data. This paper describes our submissions to the Translation Inference Across Dictionaries (TIAD) shared task of 2021. Our systems mainly rely on the MUSE and VecMap cross-lingual word embedding mapping to create new translation pairs between English, French and Portuguese data. We also create two regression models based on the graph analysis features. Our systems perform above the baseline systems.

Original language	English (Ireland)
Title of host publication	3rd Conference on Language, Data and Knowledge (LDK 2021)
Place of Publication	Zaragoza, Spain
DOIs	https://doi.org/10.13025/nxqc-n767
Publication status	Published - 1 Sep 2021

Access to Document

10.13025/nxqc-n767Licence: CC BY-NC-ND

Ahmadi2021TIADAccepted author manuscript, 358 KBLicence: CC BY-NC-ND

Cite this

@inproceedings{dc27e26ff2d34c34a3cda4cdd8c8c647,

title = "NUIG at TIAD 2021: Cross-lingual Word Embeddings for Translation Inference",

abstract = "Inducing new translation pairs across dictionaries is an important task that facilitates processing and maintaining lexicographical data. This paper describes our submissions to the Translation Inference Across Dictionaries (TIAD) shared task of 2021. Our systems mainly rely on the MUSE and VecMap cross-lingual word embedding mapping to create new translation pairs between English, French and Portuguese data. We also create two regression models based on the graph analysis features. Our systems perform above the baseline systems.",

author = "Sina Ahmadi and Ojha, \{Atul Kumar\} and Shubhanker Banerjee and McCrae, \{John Philip\}",

year = "2021",

month = sep,

day = "1",

doi = "10.13025/nxqc-n767",

language = "English (Ireland)",

booktitle = "3rd Conference on Language, Data and Knowledge (LDK 2021)",

}

TY - GEN

T1 - NUIG at TIAD 2021: Cross-lingual Word Embeddings for Translation Inference

AU - Ahmadi, Sina

AU - Ojha, Atul Kumar

AU - Banerjee, Shubhanker

AU - McCrae, John Philip

PY - 2021/9/1

Y1 - 2021/9/1

N2 - Inducing new translation pairs across dictionaries is an important task that facilitates processing and maintaining lexicographical data. This paper describes our submissions to the Translation Inference Across Dictionaries (TIAD) shared task of 2021. Our systems mainly rely on the MUSE and VecMap cross-lingual word embedding mapping to create new translation pairs between English, French and Portuguese data. We also create two regression models based on the graph analysis features. Our systems perform above the baseline systems.

AB - Inducing new translation pairs across dictionaries is an important task that facilitates processing and maintaining lexicographical data. This paper describes our submissions to the Translation Inference Across Dictionaries (TIAD) shared task of 2021. Our systems mainly rely on the MUSE and VecMap cross-lingual word embedding mapping to create new translation pairs between English, French and Portuguese data. We also create two regression models based on the graph analysis features. Our systems perform above the baseline systems.

UR - http://hdl.handle.net/10379/16973

U2 - 10.13025/nxqc-n767

DO - 10.13025/nxqc-n767

M3 - Conference Publication

BT - 3rd Conference on Language, Data and Knowledge (LDK 2021)

CY - Zaragoza, Spain

ER -

NUIG at TIAD 2021: Cross-lingual Word Embeddings for Translation Inference

Abstract

Access to Document

Other files and links

Fingerprint

Cite this